Text Mining in Bioinformatics: Research and Application
International Journal of Information Retrieval Research
Hi-index | 0.00 |
Numerous genomic annotations are currently storedin different web-accessible databanks that scientistsneed to mine with user-defined queries and in a batchmode to orderly integrate the diverse mined data insuitable user-customizable working environments.Unfortunately, to date, most accessible databanks canbe interrogated only for a single gene or protein at atime and generally the data retrieved are available inHTML page format only. We developed GeneWebEx toeffectively mine data of interest in different HTMLpages of web-based databanks, and organize extracteddata for further analyses. GeneWebEx utilizes user-definedtemplates to identify data to extract, andaggregates and structures them in a database designedto allocate the various extractions from distinctbiomolecular databanks. Moreover, a template-basedmodule enables automatic updating of extracted data.Validations performed on GeneWebEx allowed us toefficiently gather relevant annotations from varioussources, and comprehensively query them to highlightsignificant biological characteristics.